pdf2data-tools 0.0.1__tar.gz

pdf2data_tools-0.0.1/CONTRIBUTING.rst

@@ -0,0 +1,128 @@
+.. highlight:: shell
+
+============
+Contributing
+============
+
+Contributions are welcome, and they are greatly appreciated! Every little bit
+helps, and credit will always be given.
+
+You can contribute in many ways:
+
+Types of Contributions
+----------------------
+
+Report Bugs
+~~~~~~~~~~~
+
+Report bugs at https://github.com/pocoyo7798/pdf2data/issues.
+
+If you are reporting a bug, please include:
+
+* Your operating system name and version.
+* Any details about your local setup that might be helpful in troubleshooting.
+* Detailed steps to reproduce the bug.
+
+Fix Bugs
+~~~~~~~~
+
+Look through the GitHub issues for bugs. Anything tagged with "bug" and "help
+wanted" is open to whoever wants to implement it.
+
+Implement Features
+~~~~~~~~~~~~~~~~~~
+
+Look through the GitHub issues for features. Anything tagged with "enhancement"
+and "help wanted" is open to whoever wants to implement it.
+
+Write Documentation
+~~~~~~~~~~~~~~~~~~~
+
+pdf2data could always use more documentation, whether as part of the
+official pdf2data docs, in docstrings, or even on the web in blog posts,
+articles, and such.
+
+Submit Feedback
+~~~~~~~~~~~~~~~
+
+The best way to send feedback is to file an issue at https://github.com/pocoyo7798/pdf2data/issues.
+
+If you are proposing a feature:
+
+* Explain in detail how it would work.
+* Keep the scope as narrow as possible, to make it easier to implement.
+* Remember that this is a volunteer-driven project, and that contributions
+  are welcome :)
+
+Get Started!
+------------
+
+Ready to contribute? Here's how to set up `pdf2data` for local development.
+
+1. Fork the `pdf2data` repo on GitHub.
+2. Clone your fork locally::
+
+    $ git clone git@github.com:your_name_here/pdf2data.git
+
+3. Install your local copy into a virtualenv. Assuming you have virtualenvwrapper installed, this is how you set up your fork for local development::
+
+    $ mkvirtualenv pdf2data
+    $ cd pdf2data/
+    $ python setup.py develop
+
+4. Create a branch for local development::
+
+    $ git checkout -b name-of-your-bugfix-or-feature
+
+   Now you can make your changes locally.
+
+5. When you're done making changes, check that your changes pass flake8 and the
+   tests, including testing other Python versions with tox::
+
+    $ flake8 pdf2data tests
+    $ python setup.py test or pytest
+    $ tox
+
+   To get flake8 and tox, just pip install them into your virtualenv.
+
+6. Commit your changes and push your branch to GitHub::
+
+    $ git add .
+    $ git commit -m "Your detailed description of your changes."
+    $ git push origin name-of-your-bugfix-or-feature
+
+7. Submit a pull request through the GitHub website.
+
+Pull Request Guidelines
+-----------------------
+
+Before you submit a pull request, check that it meets these guidelines:
+
+1. The pull request should include tests.
+2. If the pull request adds functionality, the docs should be updated. Put
+   your new functionality into a function with a docstring, and add the
+   feature to the list in README.rst.
+3. The pull request should work for Python 3.5, 3.6, 3.7 and 3.8, and for PyPy. Check
+   https://travis-ci.com/pocoyo7798/pdf2data/pull_requests
+   and make sure that the tests pass for all supported Python versions.
+
+Tips
+----
+
+To run a subset of tests::
+
+$ pytest tests.test_pdf2data
+
+
+Deploying
+---------
+
+A reminder for the maintainers on how to deploy.
+Make sure all your changes are committed (including an entry in HISTORY.rst).
+Then run::
+
+$ bump2version patch # possible: major / minor / patch
+$ git push
+$ git push --tags
+
+Travis will then deploy to PyPI if tests pass.

pdf2data_tools-0.0.1/HISTORY.rst

@@ -0,0 +1,8 @@
+=======
+History
+=======
+
+0.0.1 (2024-01-11)
+------------------
+
+* First release on PyPI.

pdf2data_tools-0.0.1/LICENSE

@@ -0,0 +1,16 @@
+Apache Software License 2.0
+
+Copyright (c) 2024, Daniel Pereira Costa
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+

pdf2data_tools-0.0.1/MANIFEST.in

@@ -0,0 +1,11 @@
+include CONTRIBUTING.rst
+include HISTORY.rst
+include LICENSE
+include README.md
+include pyproject.toml
+
+recursive-include tests *
+recursive-exclude * __pycache__
+recursive-exclude * *.py[co]
+
+recursive-include docs *.rst conf.py Makefile make.bat *.jpg *.png *.gif

pdf2data_tools-0.0.1/PKG-INFO

@@ -0,0 +1,115 @@
+Metadata-Version: 2.4
+Name: pdf2data-tools
+Version: 0.0.1
+Summary: Transforms PDF files into machine readable JSON files
+Author-email: Daniel Pereira Costa <daniel.pereira.costa@tecnico.ulisboa.pt>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/pocoyo7798/pdf2data
+Project-URL: Repository, https://github.com/pocoyo7798/pdf2data
+Project-URL: Issues, https://github.com/pocoyo7798/pdf2data/issues
+Keywords: pdf,data-extraction,json,tables,figures,document-analysis
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: Click<=8.3.1
+Requires-Dist: PyMuPDF<=1.26.7
+Requires-Dist: pylatexenc<=2.10
+Requires-Dist: pydantic<=2.12.5
+Requires-Dist: beautifulsoup4<=4.14.3
+Requires-Dist: pdf2doi<=1.7
+Requires-Dist: Levenshtein<=0.27.3
+Requires-Dist: trieregex<=1.0.0
+Requires-Dist: bibtexparser<=1.4.3
+Requires-Dist: pypdf>=3.1.0
+Provides-Extra: test
+Requires-Dist: pytest>=3; extra == "test"
+Provides-Extra: pdf2data-pipeline
+Requires-Dist: torch<=2.10.0; extra == "pdf2data-pipeline"
+Requires-Dist: opencv-python<=4.13.0.92; extra == "pdf2data-pipeline"
+Requires-Dist: tensorflow<=2.20.0; extra == "pdf2data-pipeline"
+Requires-Dist: doclayout_yolo<=0.0.4; extra == "pdf2data-pipeline"
+Requires-Dist: pdf2image<=1.17.0; extra == "pdf2data-pipeline"
+Requires-Dist: paddleocr<=3.4.0; extra == "pdf2data-pipeline"
+Requires-Dist: paddlepaddle<=3.3.0; extra == "pdf2data-pipeline"
+Dynamic: license-file
+
+# pdf2data
+
+[![PyPI version](https://badge.fury.io/py/pdf2data-tools.svg)](https://pypi.org/project/pdf2data-tools/)
+[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+
+Transforms PDF files into machine-readable JSON files. Extracts tables, figures, text blocks, metadata, and references from scientific papers and documents.
+
+> **Note:** The repository is under active development for an article publication. Some errors are expected. Please report any issues on the [issues page](https://github.com/Pocoyo7798/pdf2data/issues).
+
+## Installation
+
+### From PyPI (recommended)
+
+```bash
+pip install pdf2data-tools
+```
+
+### With optional dependencies
+
+```bash
+# For the full PDF2Data pipeline (layout detection, OCR, etc.)
+pip install pdf2data-tools[pdf2data_pipeline]
+```
+
+### From source (development)
+
+```bash
+conda create --name pdf2data python=3.10
+conda activate pdf2data
+git clone git@github.com:Pocoyo7798/pdf2data.git
+cd pdf2data
+pip install -e .
+```
+
+## Usage
+
+### As a library
+
+```python
+from pdf2data.pdf2data_pipeline import PDF2Data
+
+pipeline = PDF2Data(
+    layout_model="DocLayout-YOLO-DocStructBench",
+    input_folder="path/to/pdfs",
+    output_folder="path/to/results",
+)
+```
+
+### Command line
+
+```bash
+# Extract tables and figures
+pdf2data_block path_to_folder path_to_results
+
+# Extract text
+pdf2data_text path_to_folder path_to_results
+
+# Extract metadata
+pdf2data_metadata path_to_folder path_to_results
+
+# Extract references
+pdf2data_references path_to_folder path_to_results
+```
+
+## License
+
+Apache Software License 2.0

pdf2data_tools-0.0.1/README.md

@@ -0,0 +1,67 @@
+# pdf2data
+
+[![PyPI version](https://badge.fury.io/py/pdf2data-tools.svg)](https://pypi.org/project/pdf2data-tools/)
+[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+
+Transforms PDF files into machine-readable JSON files. Extracts tables, figures, text blocks, metadata, and references from scientific papers and documents.
+
+> **Note:** The repository is under active development for an article publication. Some errors are expected. Please report any issues on the [issues page](https://github.com/Pocoyo7798/pdf2data/issues).
+
+## Installation
+
+### From PyPI (recommended)
+
+```bash
+pip install pdf2data-tools
+```
+
+### With optional dependencies
+
+```bash
+# For the full PDF2Data pipeline (layout detection, OCR, etc.)
+pip install pdf2data-tools[pdf2data_pipeline]
+```
+
+### From source (development)
+
+```bash
+conda create --name pdf2data python=3.10
+conda activate pdf2data
+git clone git@github.com:Pocoyo7798/pdf2data.git
+cd pdf2data
+pip install -e .
+```
+
+## Usage
+
+### As a library
+
+```python
+from pdf2data.pdf2data_pipeline import PDF2Data
+
+pipeline = PDF2Data(
+    layout_model="DocLayout-YOLO-DocStructBench",
+    input_folder="path/to/pdfs",
+    output_folder="path/to/results",
+)
+```
+
+### Command line
+
+```bash
+# Extract tables and figures
+pdf2data_block path_to_folder path_to_results
+
+# Extract text
+pdf2data_text path_to_folder path_to_results
+
+# Extract metadata
+pdf2data_metadata path_to_folder path_to_results
+
+# Extract references
+pdf2data_references path_to_folder path_to_results
+```
+
+## License
+
+Apache Software License 2.0

pdf2data_tools-0.0.1/docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = python -msphinx
+SPHINXPROJ    = pdf2data
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

pdf2data_tools-0.0.1/docs/conf.py

@@ -0,0 +1,160 @@
+#!/usr/bin/env python
+#
+# pdf2data documentation build configuration file, created by
+# sphinx-quickstart on Fri Jun  9 13:47:02 2017.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+# If extensions (or modules to document with autodoc) are in another
+# directory, add these directories to sys.path here. If the directory is
+# relative to the documentation root, use os.path.abspath to make it
+# absolute, like shown here.
+#
+import os
+import sys
+
+sys.path.insert(0, os.path.abspath(".."))
+
+import pdf2data
+
+# -- General configuration ---------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
+extensions = ["sphinx.ext.autodoc", "sphinx.ext.viewcode"]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ["_templates"]
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = ".rst"
+
+# The master toctree document.
+master_doc = "index"
+
+# General information about the project.
+project = "pdf2data"
+copyright = "2024, Daniel Pereira Costa"
+author = "Daniel Pereira Costa"
+
+# The version info for the project you're documenting, acts as replacement
+# for |version| and |release|, also used in various other places throughout
+# the built documents.
+#
+# The short X.Y version.
+version = pdf2data.__version__
+# The full version, including alpha/beta/rc tags.
+release = pdf2data.__version__
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This patterns also effect to html_static_path and html_extra_path
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = "sphinx"
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = False
+
+
+# -- Options for HTML output -------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = "alabaster"
+
+# Theme options are theme-specific and customize the look and feel of a
+# theme further.  For a list of options available for each theme, see the
+# documentation.
+#
+# html_theme_options = {}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ["_static"]
+
+
+# -- Options for HTMLHelp output ---------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = "pdf2datadoc"
+
+
+# -- Options for LaTeX output ------------------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title, author, documentclass
+# [howto, manual, or own class]).
+latex_documents = [
+    (
+        master_doc,
+        "pdf2data.tex",
+        "pdf2data Documentation",
+        "Daniel Pereira Costa",
+        "manual",
+    ),
+]
+
+
+# -- Options for manual page output ------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [(master_doc, "pdf2data", "pdf2data Documentation", [author], 1)]
+
+
+# -- Options for Texinfo output ----------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (
+        master_doc,
+        "pdf2data",
+        "pdf2data Documentation",
+        author,
+        "pdf2data",
+        "One line description of project.",
+        "Miscellaneous",
+    ),
+]

pdf2data_tools-0.0.1/docs/contributing.rst

@@ -0,0 +1 @@
+.. include:: ../CONTRIBUTING.rst

pdf2data_tools-0.0.1/docs/history.rst

@@ -0,0 +1 @@
+.. include:: ../HISTORY.rst

pdf2data_tools-0.0.1/docs/index.rst

@@ -0,0 +1,19 @@
+Welcome to pdf2data's documentation!
+======================================
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Contents:
+
+   readme
+   installation
+   usage
+   modules
+   contributing
+   history
+
+Indices and tables
+==================
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

pdf2data_tools-0.0.1/docs/installation.rst

@@ -0,0 +1,51 @@
+.. highlight:: shell
+
+============
+Installation
+============
+
+
+Stable release
+--------------
+
+To install pdf2data, run this command in your terminal:
+
+.. code-block:: console
+
+    $ pip install pdf2data
+
+This is the preferred method to install pdf2data, as it will always install the most recent stable release.
+
+If you don't have `pip`_ installed, this `Python installation guide`_ can guide
+you through the process.
+
+.. _pip: https://pip.pypa.io
+.. _Python installation guide: http://docs.python-guide.org/en/latest/starting/installation/
+
+
+From sources
+------------
+
+The sources for pdf2data can be downloaded from the `Github repo`_.
+
+You can either clone the public repository:
+
+.. code-block:: console
+
+    $ git clone git://github.com/pocoyo7798/pdf2data
+
+Or download the `tarball`_:
+
+.. code-block:: console
+
+    $ curl -OJL https://github.com/pocoyo7798/pdf2data/tarball/master
+
+Once you have a copy of the source, you can install it with:
+
+.. code-block:: console
+
+    $ python setup.py install
+
+
+.. _Github repo: https://github.com/pocoyo7798/pdf2data
+.. _tarball: https://github.com/pocoyo7798/pdf2data/tarball/master

pdf2data_tools-0.0.1/docs/make.bat

@@ -0,0 +1,36 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=python -msphinx
+)
+set SOURCEDIR=.
+set BUILDDIR=_build
+set SPHINXPROJ=pdf2data
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The Sphinx module was not found. Make sure you have Sphinx installed,
+	echo.then set the SPHINXBUILD environment variable to point to the full
+	echo.path of the 'sphinx-build' executable. Alternatively you may add the
+	echo.Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.http://sphinx-doc.org/
+	exit /b 1
+)
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS%
+
+:end
+popd

pdf2data_tools-0.0.1/docs/readme.rst

@@ -0,0 +1 @@
+.. include:: ../README.rst

pdf2data_tools-0.0.1/docs/usage.rst

@@ -0,0 +1,7 @@
+=====
+Usage
+=====
+
+To use pdf2data in a project::
+
+    import pdf2data

pdf2data_tools-0.0.1/pdf2data/__init__.py

@@ -0,0 +1,5 @@
+"""Top-level package for pdf2data."""
+
+__author__ = """Daniel Pereira Costa"""
+__email__ = "daniel.pereira.costa@tecnico.ulisboa.pt"
+__version__ = "0.0.1"